Triple

T19397024
Position Surface form Disambiguated ID Type / Status
Subject Colindale Underground station E485217 entity
Predicate hasStationCode P1289 FINISHED
Object CND
CND is the three-letter station code used to identify Colindale Underground station on the London Underground network.
 E1373666 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: CND | Statement: [Colindale Underground station, hasStationCode, CND]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CND
Context triple: [Colindale Underground station, hasStationCode, CND]
  • A. CND
    CND is a British peace organization best known for campaigning against nuclear weapons and promoting global disarmament.
  • B. CND
    CND is the IATA airport code for Mihail Kogălniceanu International Airport serving Constanța, Romania.
  • C. CND
    CND is the United Nations Commission on Narcotic Drugs, the central policymaking body for international drug control.
  • D. CND
    CND is a professional nail care brand known for its innovative nail polish, gel, and enhancement systems used widely in salons.
  • E. CND
    CND is the commonly used abbreviation for the Compañía Nacional de Danza, Spain’s principal national dance company known for its contemporary and classical ballet repertoire.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: CND
Triple: [Colindale Underground station, hasStationCode, CND]
Generated description
CND is the three-letter station code used to identify Colindale Underground station on the London Underground network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CND
Target entity description: CND is the three-letter station code used to identify Colindale Underground station on the London Underground network.
  • A. CND
    CND is a British peace organization best known for campaigning against nuclear weapons and promoting global disarmament.
  • B. CND
    CND is the IATA airport code for Mihail Kogălniceanu International Airport serving Constanța, Romania.
  • C. CND
    CND is a professional nail care brand known for its innovative nail polish, gel, and enhancement systems used widely in salons.
  • D. CND
    CND is the United Nations Commission on Narcotic Drugs, the central policymaking body for international drug control.
  • E. CND
    CND is the commonly used abbreviation for the Compañía Nacional de Danza, Spain’s principal national dance company known for its contemporary and classical ballet repertoire.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8e8d5162481909db12435d9535c1a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e62573f5788190a635b92121db2cf7 completed April 20, 2026, 1:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a072b8dd70c8190870a8478a111b887 completed May 15, 2026, 2:19 p.m.
NEDg Description generation batch_6a072e41ca0c8190a6d85eaa76d00de8 completed May 15, 2026, 2:31 p.m.
NED2 Entity disambiguation (via description) batch_6a072eb872b88190904f9947228066fb completed May 15, 2026, 2:33 p.m.
Created at: April 10, 2026, 1:36 p.m.